Search

Many countries consider clay rock formations as potential host rocks for high-level nuclear waste disposal. Clay rocks may exhibit heterogeneity on various scales, from the micro- to the facies-scale. In the Mont Terri rock laboratory, Switzerland, various experiments study properties and characteristics of the Jurassic Opalinus Clay, which is the target host rock for the Swiss nuclear waste repository but may also provide proxies for other considered clay rock formations. At Mont Terri, the Opalinus Clay mainly appears in a shaly and two sandy facies. So far, diffusion experiments at Mont Terri focussed on the relatively homogeneous shaly facies. The upper sandy facies (SF-OPA) exhibits a more pronounced internal – mineralogical and textural – heterogeneity. Clay rocks with comparable heterogeneity to SF-OPA may be present among the lower Cretaceous clay rocks of northern Germany, which are among the potential host rock candidates for a future German nuclear waste repository. Since 2020, seven institutions develop an in-situ diffusion experiment in SF-OPA, the so-called DR-D experiment, to explore the impact of rock heterogeneity on radionuclide diffusion in low permeability clay rocks. So far, the DR-D experiment combined high-resolution seismic tomography, borehole logging, and detailed drill core analyses to characterize the heterogeneity of the selected SF-OPA area. The targeted rock zone exhibits a layer starting ca. 10 m below the gallery surface, which is characterized by relatively high seismic velocities. This layer is as well evident in the natural gamma- and the neutron backscattering logs. In the drill cores it stands out as whitish rock characterized by large concretions and traces of bioturbation in contrast to the dark layered clay-rock above and below with smaller concretions. Detailed analysis of seismic signals and drill-cores is still ongoing. In future, an in-situ diffusion test using various radioactive and non-radioactive tracers (e.g., HTO, 1

Ensuring the accuracy of the estimated time of arrival (ETA) information for ships approaching ports and inland terminals is increasingly critical today. Waterway transportation plays a vital role in freight transportation and has a significant ecological impact. Improving the accuracy of ETA predictions can enhance the reliability of inland waterway shipping, increasing the acceptance of this eco-friendly mode of transportation. This study compares the industry-standard approach for predicting the ETA based on average travel times with a neural network (NN) trained using real-world historical data. This study generates and trains two NN models using historical ship position data. These models are then assessed and contrasted with the conventional method of calculating average travel times for two specific areas in the Netherlands and Germany. The results indicate by using specific input features, the quality of ETA predictions can improve by an average of 20.6% for short trips, 4.8% for medium-length trips, and 13.4% for long-haul journeys when compared to the average calculation., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

A Dynamically Configurable Autonomous Vehicle (DCAV) is a new class of autonomous vehicle concept using a separable design of lower and upper parts—carriers and modules—to allow more flexible operation. A fleet of DCAVs consists of a set of carriers and a set of compatible modules. Different, possibly crowd-sourced, modules can increase the number of use-cases for DCAVs, possibly leading to disruptive changes in the transport sector. This study investigates the use of DCAV system operating on an Autonomous Mobility-on-Demand (AMoD) scenario, combining passenger and freight transport flows. The novel problem is denoted as the Dynamically Configurable Autonomous Vehicle Pickup and Delivery Problem (DCAVPDP). We propose a mixed-integer linear programming (MILP) model aiming to minimize DCAV-fleet size and distance traveled. We compare the performance of a DCAV fleet to the performance of a typical single-purpose fleet (consisting of dedicated passenger and freight vehicles). The numerical study, with 360 instances for each fleet type, considering four people-and-freight demand distribution scenarios, the inclusion of ridesharing, module-and-carrier (de)coupling locations, and different simulation horizon lengths, shows that the proposed modular DCAV system can fulfill a mixed people-and-freight demand using, on average, 18.77% fewer carriers than a regular AMoD system comprised of single-purpose vehicles while increasing on-duty fleet utilization by 4.82%., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

Transport Engineering and Logistics

Transport Engineering and Logistics

Travel to intercity transportation hubs, such as railway stations and airports, can be the most troublesome and inefficient part of the entire air/railway travel journey, as travelers often carry large luggage and have stringent arrival time requirements. Taking public transportation, such as metro and bus services, is inconvenient to carry luggage and less reliable in arrival time while taking taxi services could be less economical. As a result, providing reliable and convenient yet economical on-demand first-mile services for travelers to intercity transportation hubs is essential. This paper proposes a ridesharing approach for the first-mile transport system for travelers heading towards the intercity transportation hub and develops a mixed-integer linear programming (MILP) model with the objective of minimizing the total operating costs for ridesharing service operators. The MILP model considers (1) large luggage that may occupy seats when the car trunk is not large enough to place them; (2) passengers’ requirements on arrival time and ride time; and (3) travel time uncertainty ensuring that riders’ arrival time and ride time can be satisfied. A tailored adaptive large neighborhood search algorithm with an acceleration strategy is developed for obtaining robust near-optimal solutions within a reasonable time. To assess the solution quality, the MILP model is reformulated as a set-partitioning model, and the column generation algorithm is leveraged to determine a tight lower bound; a greedy algorithm is introduced to obtain an upper bound. Computational experiments on Shanghai South Railway Station demonstrate that ridesharing is an effective strategy for reducing overall travel costs while meeting the first-mile travel demand. In addition, it is essential to consider luggage and travel time uncertainty for determining ridesharing schemes., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

Modern ports face significant challenges as strategic nodes of global supply chains, being responsible for the coordination of inbound and outbound flows at deep-sea and in hinterland transport corridors. Digitization and the adoption of disruptive technologies can help ports to tide over operational challenges. Automated Ground Vehicles (AGVs) are an integral part of operations at many modern ports, especially inside container terminals. With the shift to automated transport outside of the terminal areas, these AGVs may form platoons to establish an efficient port hinterland transport corridor. In this work, we propose a new robust optimization approach to assess the time and cost-efficiency of applying such AGV platoons in a container pickup and delivery problem. We develop a bi-objective mixed-integer programming model, which simultaneously minimizes time and cost elements, and also considers emissions. Each transportation task can be carried out by AGVs or conventional trucks, while the number of available vehicles for each mode is uncertain (as they are used to connect different modalities of container transport). The robust optimization model is based on an ellipsoidal uncertainty set to handle this uncertainty and an augmented epsilon constraint method to obtain Pareto-optimal solutions for this multi-objective problem. The developed framework is evaluated in two case studies: the Port of Rotterdam in The Netherlands and the Port of Valparaíso in Chile, with different traveling distances in corridors to a dry port (200 km) and a pre-terminal (11 km), respectively. The results indicate that the new direct delivery scheme by AGV platoons is significantly more cost- and time-efficient than the benchmark and provides a low-carbon emission transportation mode. While the benefits of decreased dwell times (56% on average) and carbon emissions (on average by 10%) are similar for short and long traveling distances, the savings in cost increase (from 4.9% to 8%) wit, Rivers, Ports, Waterways and Dredging Engineering, Transport Engineering and Logistics

Increasing online retail has resulted in increased automation in order picking systems, leading to new challenges and opportunities in task scheduling. The job-shop scheduling problem is an optimization problem essential in such systems, but existing JSP literature often overlooks workplace fatigue, which harms employees’ well-being and costs U.S. employers up to €127 billion annually. In this work, we propose fatigue consideration in the job-shop scheduling problem in a cobotic order picking system to mitigate its negative effects. We present a new bi-objective mixed integer nonlinear programming problem formulation that considers worker fatigue and productivity during schedule optimisation. To put the results of simulated optimisation in perspective, we experimentally validate the fatigue model and scheduling results in a real operation. The mathematical model finds solutions that conventional single-objective optimisation cannot, allowing fractional fatigue distribution improvements more than 4x larger than the decrease in productivity they require in 53% of the considered virtual cases. The experiments show that our predictive fatigue model has an average RMSE of 2.20 kcal/min in estimating energy expenditure rates compared to heart rate measurements. It also shows a low correlation, meaning it is unfit for application. On the other hand, fatigue-conscious schedules show no clear benefit regarding measured and perceived fatigue. However, the scheduling model could also use heart rate measurements that do not show these inaccuracies. Our study highlights the need to further develop and validate the mathematical formulation and fatigue model and extend to other human factors and indirect fatigue effects., Human-Centred Artificial Intelligence, Human-Robot Interaction, Transport Engineering and Logistics

Storage space management in bulk terminals has become an important focus for research and practical operation due to the increasing demand for bulk cargo and limited storage space in stockyards. The study of storage space management in dry bulk terminals is less thorough and comprehensive, and the existing research investigates the storage space allocation problem with other operational problems like berth allocation problems, but little environmental consideration has been incorporated. We investigate the storage space allocation problem with the consideration of stacker-reclaimer assignment and mist cannon operation to deal with the dust generated during material stacking. A mixed integer programming model has been established with the aim of minimizing energy consumption to reflect the pursuit of the growing emphasis on climate-neutral operations and sustainability. We test the effectiveness of the model by conducting computational experiments. We use the commercial solver CPLEX to obtain the optimal solutions for most of the test instances. Useful managerial insights extracted from the computational results may serve as a reference for storage space management in dry bulk terminals., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

Biomechatronics & Human-Machine Control, Team Azita Dabiri, Transport Engineering and Logistics, Intelligent Vehicles

Carriers can remarkably reduce transportation costs and emissions when they collaborate, for example through a platform. Such gains, however, have only been investigated for relatively small problem instances with low numbers of carriers. We develop auction-based methods for large-scale dynamic collaborative pickup and delivery problems, combining techniques of multi-agent systems and combinatorial auctions. We evaluate our approach in terms of both solution quality and possibilities of strategic behaviour using a real-world data set of over 12,000 orders. Hence, this study is (to the best of our knowledge) the first to assess the benefits of large-scale carrier cooperation and to propose an approach for it. First, we use iterative single-order auctions to investigate possible collaboration gains for increasing numbers of carriers. Our results show that travel costs can be reduced by up to 77% when 1000 carriers collaborate, largely increasing the gains that were previously observed in smaller-scale collaboration. We also ensure that individual rationality is guaranteed in each auction. Next, we compare this approach of multiple local auctions with an established central combinatorial auction mechanism and observe that the proposed approach performs better on large-scale instances. Furthermore, to improve solution quality, we integrate the two approaches by allowing small bundle auctions in the multi-agent system. We analyze the circumstances under which bundling is beneficial in a large-scale decentralized system and demonstrate that travel cost gains of up to 13% can be obtained for 1000 carriers. Finally, we investigate whether the system is vulnerable to cheating: we show that misrepresentation of true values by individual participants sometimes can benefit them at the cost of the collective. Although such strategic behaviour is not straightforward, we also discuss different means to prevent it., Transport Engineering and Logistics, Algorithmics

With the popularization of transportation network companies (TNCs) (e.g., Uber, Lyft) and the rise of autonomous vehicles (AVs), even major car manufacturers are increasingly considering themselves as autonomous mobility-on-demand (AMoD) providers rather than individual vehicle sellers. However, matching the convenience of owning a vehicle requires providing consistent service quality, taking into account individual expectations. Typically, different classes of users have different service quality (SQ) expectations in terms of responsiveness, reliability, and privacy. Nonetheless, AMoD systems presented in the literature do not enable active control of service quality in the short term, especially in light of unusual demand patterns, sometimes allowing extensive delays and user rejections. This study proposes a method to control the daily operations of an AMoD system that uses the SQ expectations of heterogeneous user classes to dynamically distribute service quality among riders. Additionally, we consider an elastic vehicle supply, that is, privately-owned freelance AVs (FAVs) can be hired on short notice to help providers meeting user service-level expectations. We formalize the problem as the dial-a-ride problem with service quality contracts (DARP-SQC) and propose a multi-objective matheuristic to address real-world requests from Manhattan, New York City. Applying the proposed service-level constraints, we improve user satisfaction (in terms of reached service-level expectations) by 53% on average compared to conventional ridesharing systems, even without hiring additional vehicles. By deploying service-quality-oriented on-demand hiring, our hierarchical optimization approach allows providers to adequately cater to each segment of the customer base without necessarily owning large fleets., Transport Engineering and Logistics, Learning & Autonomous Control

Traditionally, terminal operators create an initial berthing plan before the arrival of incoming vessels. This plan involves decisions on when and where to load or discharge containers for the calling vessels. However, disruptive unforeseen events (i.e., arrival delays, equipment breakdowns, tides, or extreme weather) interfere with the implementation of this initial plan. For terminals, berths and quay cranes are both crucial resources, and their capacity limits the efficiency of port operations. Thus, one way to minimize the adverse effects caused by disruption is to ally different terminals to share berthing resources. In some challenging situations, terminal operators also need to consider the extensive transshipment connections between feeder and mother vessels. Therefore, in this work, we investigate a collaborative variant of the berth allocation recovery problem which focuses on the collaboration among terminals and transshipment connections between vessels. We propose a mixed-integer programming model to (re)-optimize the initial berth and quay crane allocation plan and develop a Squeaky Wheel Optimization metaheuristic to find near-optimal solutions for large-scale instances. The results from the performed computational experiments, considering multiple scenarios with disruptive events, show consistent improvements of up to 40% for the suggested collaborative strategy (in terms of costs for the terminal operators)., Transport Engineering and Logistics

Current mobility services cannot compete on equal terms with self-owned mobility products concerning service quality. Because of supply and demand imbalances, ridesharing users invariably experience delays, price surges, and rejections. Traditional approaches often fail to respond to demand fluctuations adequately because service levels are, to some extent, bounded by fleet size. With the emergence of autonomous vehicles, however, the characteristics of mobility services change and new opportunities to overcome the prevailing limitations arise. In this paper, we consider an autonomous ridesharing problem in which idle vehicles are hired on-demand in order to meet the service-level requirements of a heterogeneous user base. In the face of uncertain demand and idle vehicle supply, we propose a learning-based optimization approach that uses the dual variables of the underlying assignment problem to iteratively approximate the marginal value of vehicles at each time and location under different availability settings. These approximations are used in the objective function of the optimization problem to dispatch, rebalance, and occasionally hire idle third-party vehicles in a high-resolution transportation network of Manhattan, New York City. The results show that the proposed policy outperforms a reactive optimization approach in a variety of vehicle availability scenarios while hiring fewer vehicles. Moreover, we demonstrate that mobility services can offer strict service-level contracts to different user groups featuring both delay and rejection penalties., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

Contains fulltext : 288357.pdf (Publisher’s version ) (Open Access), For the sizeable subset of adolescents and young adults whose cancer is incurable, developmentally appropriate end-of-life discussions are critical. Standards of care for adolescent and young adult end-of-life communication have been established, however, many health-professionals do not feel confident leading these conversations, leaving gaps in the implementation of best-practice end-of-life communication. We present a protocol for a Delphi study informing the development and implementation of clinician training to strengthen health-professionals' capacity in end-of-life conversations. Our approach will inform training to address barriers to end-of-life communication with adolescents and young adults across Westernized Adolescent and Young Adult Cancer Global Accord countries. The Adolescent and Young Adult Cancer Global Accord team involves 26 investigators from Australia, New Zealand, the United States, Canada and the United Kingdom. Twenty-four consumers, including adolescents and young adults with cancer history and carers, informed study design. We describe methodology for a modified Delphi questionnaire. The questionnaire aims to determine optimal timing for end-of-life communication with adolescents and young adults, practice-related content needed in clinician training for end-of-life communication with adolescents and young adults, and desireability of evidence-based training models. Round 1 involves an expert panel of investigators identifying appropriate questionnaire items. Rounds 2 and 3 involve questionnaires of international multidisciplinary health-professionals, followed by further input by adolescents and young adults. A second stage of research will design health-professional training to support best-practice end-of-life communication. The outcomes of this iterative and participatory research will directly inform the implementation of best-practice end-of-life communication across Adolescent and Young Adult Cancer Global Accord countries. Barrie

Berth allocation is fundamental to port-related operations in maritime shipping. Port managers have to deal with the increasing demands either by expanding the terminals or by improving efficiency to maintain competitiveness. Port expansion is a long-term project, and it requires much capital investment. Thus, the question of how to enhance the efficiency of berth allocation has received much research interest. Research on the Berth Allocation Problem (BAP) in container ports is quite advanced. However, only limited research focuses on BAP in bulk ports, although some similarities exist. Contributing to Operations Research approaches on the BAP, this paper develops a hybrid BAP mixed-integer optimization model dedicated to bulk ports. In addition to considering the handling characteristics of bulk ports, we also incorporate more practical factors such as unavailability and stock levels. The objective of the proposed model is to minimize the demurrage fee for all vessels under consideration of unavailability and stock constraints. We use the commercial software CPLEX to obtain the optimal solutions for a set of distinct instances, explicitly considering the situation of multiple cargo types on one vessel, which provides a better fit for the loading or discharging operations in real-world bulk ports. This is the first study to our knowledge that dedicates itself to the BAP in bulk ports and considers unavailability and stock constraints simultaneously. Our solutions can provide timely and effective decision support to bulk port managers., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

Pain in children living with and beyond cancer is understudied and undertreated. Pain science education (PSE) is a conceptual change strategy facilitating patients' understanding of the biopsychosocial aspects of pain. Preliminary studies on the adaptation of PSE interventions to adults with and beyond cancer provide a foundation for pediatric research. PSE could help childhood cancer survivors experiencing persistent pain and pain-related worry after active treatment. PSE may also help children receiving cancer treatment, providing them with a foundation of adaptive pain beliefs and cognitions, and preparing them for procedural and treatment-related pain. We direct this paper toward pediatric oncology clinicians, policy makers, and researchers working with children living with and beyond cancer. We aim to (a) identify challenges in adapting PSE for children living with and beyond cancer, (b) offer possible solutions, and (c) propose research questions to guide the implementation of PSE for children living with and beyond cancer.

Next to environmental aspects, establishing areas for safe and economically viable automated driving in mixed-traffic settings is one major challenge for sustainable development of Autonomous Vehicles (AVs). This work investigates safety in the interactions between AVs, human-driven vehicles, and vulnerable road users, including cyclists and pedestrians, within a simulated urban environment in the Dutch city of Rotterdam. New junction and pedestrian models are introduced, and virtual AVs with an occlusion-aware driving system are deployed to deliver cargo autonomously. The safety of applying this autonomous cargo delivery service is assessed using a large set of Surrogate Safety Indicators (SSIs). Furthermore, Macroscopic Fundamental Diagrams (MFDs) and travel time loss are incorporated to evaluate the network efficiency. By assessing the impact of various measures involving Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), Vehicle-to-Everything (V2X) communications, infrastructure modifications, and driving behavior, we show that traffic safety and network efficiency can be achieved in a living lab setting for the considered case. Our findings further suggest that V2X gets implemented, new buildings are not placed close to intersections, and the speed limit of non-arterial roads is lowered., Rivers, Ports, Waterways and Dredging Engineering, Transport Engineering and Logistics

The trends of autonomous transportation and mobility on demand in line with large numbers of requests increasingly call for decentralized vehicle routing optimization. Multi-agent systems (MASs) allow to model fully autonomous decentralized decision making, but are rarely considered in current decision support approaches. We propose a multi-agent approach in which autonomous vehicles are modeled as independent decision makers that locally interact with auctioneers for transportation orders. The developed MAS finds solutions for a realistic routing problem in which multiple pickup and delivery alternatives are possible per order. Although information sharing is significantly restricted, the MAS results in better solutions than a centralized Adaptive Large Neighborhood Search with full information sharing on large problem instances where computation time is limited., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics, Algorithmics

Collaboration in transportation is important to reduce costs and emissions, but carriers may have incentives to bid strategically in decentralized auction systems. We investigate what the effect of the auction strategy is on the possible cheating benefits in a dynamic context, such that we can recommend a method with lower chances for carriers to cheat. We consider both a first-price auction system and a second-price auction scheme. Contrary to what was expected, a second-price auction scheme gives more room for successful strategic behaviour, while it also results in more rejected orders. A first-price auction scheme might be useful in practice if the profit shares that are allocated to the winner of an auction are selected carefully., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics, Algorithmics

The craft beer supply chain in the USA differs from the supply chain of macro breweries in its structure, handled volumes and product shelf-life. In this work, we study how these smaller craft breweries can benefit from transparency in their supply chain. We consider additional information sharing of orders and inventories at downstream nodes. The levels that we investigate grant the brewery incremental access to distributor, wholesaler, and retailer data. We show how this knowledge can be incorporated effectively into the brewery’s production planning strategy. Extending the well-known beer game, we conduct a simulation study using real-world craft beer supply chain parameters and demand. We quantify the impact of information sharing on the craft brewery’s sales, spoilage, and beer quality. Our model is designed to directly support the brewery when evaluating the value of downstream information and negotiating data purchases with brokers. Through a computational analysis, we show that the brewery’s benefits increase almost linearly with every downstream node that it gets data from. Full transparency allows to halve the missed beer sales, and beer spoilage can even be reduced by 70% on average., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

The shared autonomous vehicle (SAV) is a new concept that meets the upcoming trends of autonomous driving and changing demands in urban transportation. SAVs can carry passengers and parcels simultaneously, making use of dedicated passenger and parcel modules on board. A fleet of SAVs could partly take over private transport, taxi, and last-mile delivery services. A reduced fleet size compared to conventional transportation modes would lead to less traffic congestion in urban centres. This paper presents a method to estimate the optimal capacity for the passenger and parcel compartments of SAVs. The problem is presented as a vehicle routing problem and is named variable capacity share-a-ride-problem (VCSARP). The model has a MILP formulation and is solved using a commercial solver. It seeks to create the optimal routing schedule between a randomly generated set of pick-up and drop-off requests of passengers and parcels. The objective function aims to minimize the total energy costs of each schedule, which is a trade-off between travelled distance and vehicle capacity. Different scenarios are composed by altering parameters, representing travel demand at different times of the day. The model results show the optimized cost of each simulation along with associated routes and vehicle capacities., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

Human aspects in collaboration of humans and robots, as common in warehousing, are considered increasingly important objectives in operations management. In this work, we let robots learn about human stress levels based on sensor data in collaborative order picking of robotic mobile fulfillment systems. To this end, we develop a multi-agent reinforcement (MARL) approach that considers human stress levels and recovery behavior next to traditional performance objectives in the reward function of robotic agents. We assume a human-oriented assignment problem in which the robotic agents assign orders and short breaks to human workers based on their stress/recovery states. We find that the proposed MARL policy reduces the human stress time by up 50% in comparison to the applied benchmark policies and maintains system efficiency at a comparable level. While the results may need to be confirmed in different settings considering different types of humans aspects and efficiency objectives, they also show a practicable pathway to control stress levels and recovery for related problems of human-robot collaboration, inside and outside of warehousing., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport Engineering and Logistics

Human aspects in collaboration of humans and robots, as common in warehousing, are considered increasingly important objectives in operations management. This work aims to let robots learn about human discomfort in collaborative order picking of robotic mobile fulfillment systems. To this end, a multi-agent reinforcement (MARL) approach that considers human discomfort next to traditional performance objectives in the reward function of robotic agents is developed. As a first step, we assume a human-oriented assignment problem in which the robotic agents assign orders to human workers at order picking work stations. The results show that among the four evaluated assignment policies, only the proposed MARL policy effectively considers human discomfort. While the approach may need to be refined to obtain near-optimal solutions for the trade-off between humans aspects and efficiency objectives, it also shows a practicable pathway for related problems of human-robot collaboration, inside and outside of warehousing., Transport Engineering and Logistics